Structural Engineering and Mechanics

  • 제91권6호
  • /
  • Pages.583-589
  • /
  • 2024
  • /
  • 1225-4568(pISSN)
  • /
  • 1598-6217(eISSN)
테크노프레스 (Techno-Press)
권호 표지
DOI QR코드

DOI QR Code

Study on the applicability of regression models and machine learning models for predicting concrete compressive strength

  • Sangwoo Kim (Department of Civil Engineering, Gyeongsang National University) ;
  • Jinsup Kim (Department of Civil Engineering, Gyeongsang National University) ;
  • Jaeho Shin (Department of Information and Statistics, Gyeongsang National University) ;
  • Youngsoon Kim (Department of Information and Statistics and Dept. of Bio & Medical Bigdata (BK21 Four Program), Gyeongsang National University)
  • 투고 : 2024.07.01
  • 심사 : 2024.08.30
  • 발행 : 2024.09.25
⟨ 이전 논문 다음 논문 ⟩

초록

Accurately predicting the strength of concrete is vital for ensuring the safety and durability of structures, thereby contributing to time and cost savings throughout the design and construction phases. The compressive strength of concrete is determined by various material factors, including the type of cement, composition ratios of concrete mixtures, curing time, and environmental conditions. While mix design establishes the proportions of each material for concrete, predicting strength before experimental measurement remains a challenging task. In this study, Abrams's law was chosen as a representative investigative approach to estimating concrete compressive strength. Abrams asserted that concrete compressive strength depends solely on the water-cement ratio and proposed a logarithmic linear relationship. However, Abrams's law is only applicable to concrete using cement as the sole binding material and may not be suitable for modern concrete mixtures. Therefore, this research aims to predict concrete compressive strength by applying various conventional regression analyses and machine learning methods. Six models were selected based on performance experiment data collected from various literature sources on different concrete mixtures. The models were assessed using Root Mean Squared Error (RMSE) and coefficient of determination (R2) to identify the optimal model.

키워드

과제정보

This work was supported by the Ministry of Education of the Republic of Korea and the National Research Foundation of Korea (RS-2023-00248882). This work was also supported by the MSIT (Ministry of Science and ICT, Korea, under the ICAN (ICT Challenge and Advanced Network of HRD) program (IITP-2024-RS-2022-00156409), supervised by IITP (Institute of Information & Communications Technology Planning & Evaluation).

참고문헌

  1. Ahmad, W., Ahmad, A. and Ostrowski, K.A. (2021), "Sustainable approach of using sugarcane bagasse ash in cement-based composites: A systematic review", Case Stud. Constr. Mater., 15, 1-28. https://doi.org/10.1016/j.cscm.2021.e00698.
  2. Ali, J., Khan, R., Ahmad, N. and Maqsood, I. (2012), "Random forests and decision trees", Int. J. Comput. Sci. Iss., 9(5), 272-278.
  3. Altun, F., Kisi, O. and Aydin, K. (2008), "Predicting the compressive strength of steel fiber added lightweight concrete using neural network", Comput. Mater. Sci., 42(2), 259-265. https://doi.org/10.1016/j.commatsci.2007.07.011.
  4. Atici, U. (2010), "Prediction of the strength of mineral addition concrete using regression analysis", Mag. Concrete Res., 62(8), 585-592. https://doi.org/10.1680/macr.2010.62.8.585.
  5. Boukhatem, B., Kenai, S., Tagnit-Hamou, A. and Ghrici, M. (2011), "Application of new information technology on concrete: an overview", J. Civil Eng. Manage., 17(2), 248-258. https://doi.org/10.3846/13923730.2011.574343.
  6. Breiman, L. (2001), "Random forests", Mach. Learn., 45, 5-32. https://doi.org/10.1023/A:1010933404324.
  7. Chou, J.S., Chiu, C.K., Farfoura, M. and Al-Taharwa, I. (2011), "Optimizing the prediction accuracy of concrete compressive strength based on a comparison of data-mining techniques", J. Comput. Civil Eng., 25(3), 242-253. https://doi.org/10.1061/(ASCE)CP.1943-5487.00000.
  8. Chou, J.S., Tsai, C.F., Pham, A.D. and Lu, Y.H. (2014), "Machine learning in concrete strength simulations: Multi-nation data analytics", Constr. Build. Mater., 73, 771-780. https://doi.org/10.1016/j.conbuildmat.2014.09.054.
  9. Cover, T. and Hart, P. (1967), "Nearest neighbor pattern classification", IEEE Trans. Inform. Theory, 13, 21-27. https://doi.org/10.1109/TIT.1967.1053964.
  10. Danial, J.A., Haleh, R. and Panagiotis, G.A. (2024), "An advanced machine learning technique to predict compressive strength of green concrete incorporating waste foundry sand", Comput. Concrete, 33(1), 77-90. https://doi.org/10.12989/cac.2024.33.1.077.
  11. Dutta, S., Samui, P. and Kim, D. (2018), "Comparison of machine learning techniques to predict the compressive strength of concrete", Comput. Concrete, 21(4), 463-470. https://doi.org/10.12989/cac.2018.21.4.463.
  12. Garg, A., Sharma, A., Li, L., Zheng, W., Lee, B.S. and Raman, R. (2024), "Uncertainty evaluation in density and viscosity of nanofluids at different temperatures using Gaussian process regression-based Monte-Carlo simulations", J. Molecul. Liquid., 411, 125794. https://doi.org/10.1016/j.molliq.2024.125794.
  13. Gupta, S.M. (2007), "Support vector machines based modelling of concrete strength", World Acad. Sci. Eng. Technol., 36(1), 305-311.
  14. Ho, T.K. (1995), "Random decision forests", Proceedings of 3rd International Conference on Document Analysis and Recognition, 1, 278-282.
  15. Hosseini, P., Booshehrian, A., Delkash, M., Ghavami, S. and Zanjani, M.K. (2009), "Use of nano-SiO2 to improve microstructure and compressive strength of recycled aggregate concretes", Nanotechnology in Construction 3: Proceedings of the NICOM3, Springer Berlin Heidelberg.
  16. Imandoust, S.B. and Bolandraftar, M. (2013), "Application of k-nearest neighbor (knn) approach for predicting economic events: Theoretical background", Int. J. Eng. Res. Appl., 3(5), 605-610.
  17. Kaveh, M., Emadaldin. M.G., Majid, S. and Alireza, S. (2021), "Modeling the mechanical properties of rubberized concrete using machine learning methods", Comput. Concrete, 28(6), 567-583. https://doi.org/10.12989/cac.2021.28.6.567.
  18. Lee, J.J., Kim, D., Chang, S.K. and Nocete, C.F.M. (2009), "An improved application technique of the adaptive probabilistic neural network for predicting concrete strength", Comput. Mater. Sci., 44(3), 988-998. https://doi.org/10.1016/j.commatsci.2008.07.012.
  19. Lim, C.H., Yoon, Y.S. and Kim, J.H. (2004), "Genetic algorithm in mix proportioning of high-performance concrete", Cement Concrete Res., 34(3), 409-420. https://doi.org/10.1016/j.cemconres.2003.08.018.
  20. Majid, A., Khan, A., Javed, G. and Mirza, A.M. (2010), "Lattice constant prediction of cubic and monoclinic perovskites using neural networks and support vector regression", Comput. Mater. Sci., 50(20), 363-372. https://doi.org/10.1016/j.commatsci.2010.08.028.
  21. Mendes, E., Watson, I., Triggs, C., Mosley, N. and Counsell, S. (2003), "A comparative study of cost estimation models for web hypermedia applications", Empir. Softw. Eng., 8(2), 163-196. https://doi.org/10.1023/A:1023062629183.
  22. Mondal, A. and Bhanja, S. (2022), "Augmentation of Abrams law for fly ash concrete", Mater. Today: Proc., 65, 644-650. https://doi.org/10.1016/j.matpr.2022.03.204.
  23. Mousavi, S.M., Aminian, P., Gandomi, A.H., Alavi, A.H. and Bolandi, H. (2012), "A new predictive model for compressive strength of HPC using gene expression programming", Adv. Eng. Softw., 45(1), 105-114. https://doi.org/10.1016/j.advengsoft.2011.09.014.
  24. Muliauwan, H.N., Prayogo, D., Gaby, G. and Harsono, K. (2020), "Prediction of concrete compressive strength using artificial intelligence methods", J. Phys. Conf. Ser., 1625(1), 012018. https://doi.org/10.1088/1742-6596/1625/1/012018.
  25. Ozcan, G., Kocak, Y, and Gulbandilar, E. (2017), "Estimation of compressive strength of BFS and WTRP blended cement mortars with machine learning models", Comput. Concrete, 19(3), 275-282. https://doi.org/10.12989/cac.2017.19.3.275.
  26. Pazouki, G., Tao, Z., Saeed, N. and Kang, W. (2023), "Using artificial intelligence methods to predict the compressive strength of concrete containing sugarcane bagasse ash", Constr. Build. Mater., 409, 134047. https://doi.org/10.1016/j.conbuildmat.2023.134047.
  27. Quinlan, J.R. (1986), "Induction of decision trees", Mach. Learn., 1, 81-106.
  28. Sagar, P., Ibadur, R. and Asif, H. (2023), "Comparative studies of different machine learning algorithms in predicting the compressive strength of geopolymer concrete", Comput. Concrete, 32(6), 607-613. https://doi.org/10.12989/cac.2023.32.6.607.
  29. Segal, M.R. (2004), "Machine learning benchmarks and random forest regression", UCSF: Center for Bioinformatics and Molecular Biostatistics.
  30. Sharma, A., Li, L., Garg, A. and Lee, B. S. (2024), "Probe into the volumetric properties of binary mixtures: Essence of regression-based machine learning algorithms", J. Molec. Liquid., 399, 124498. https://doi.org/10.1016/j.molliq.2024.124498.
  31. Shukla, N.K., Garg, A., Bhutto, J., Aggarwal, M., Abbas, M., Hussein, H.S., ... & Khan, T.Y. (2023b), "Predicting the compressive strength of SCC containing nano silica using surrogate machine learning algorithms", Comput. Concrete, 32(4), 373-381. https://doi.org/10.12989/cac.2023.32.4.373.
  32. Shukla, N.K., Garg, A., Bhutto, J., Aggarwal, M., Raja, M.R., Hussein, H.S., ... & Sabherwal, P. (2023a), "An insight into the prediction of mechanical properties of concrete using machine learning techniques", Comput. Concrete, 32(3), 263-286. https://doi.org/10.12989/cac.2023.32.3.263.
  33. Tiryaki, S. and Aydin, A. (2014), "An artificial neural network model for predicting compression strength of heat treated woods and comparison with a multiple linear regression model", Constr. Build. Mater., 62(15), 102-108. https://doi.org/10.1016/j.conbuildmat.2014.03.041.
  34. Tso, G.K.F. and Yau, K.K.W. (2007), "Predicting electricity energy consumption: A comparison of regression analysis, decision tree and neural networks", Energy, 32(9), 1761-1768. https://doi.org/10.1016/j.energy.2006.11.010.
  35. Unlu, R. (2020), "An assessment of machine learning models for slump flow and examining redundant features", Comput. Concrete, 25(6), 565-574. https://doi.org/10.12989/cac.2020.25.6.565.
  36. Yan, K. and Shi, C. (2010), "Prediction of elastic modulus of normal and high strength concrete by support vector machine", Constr. Build. Mater., 24(8), 1479-1485. https://doi.org/10.1016/j.conbuildmat.2010.01.006.
  37. Yeh, I.C. (1998), "Modeling of strength of high performance concrete using artificial neural networks", Cement Concrete Res., 28(12), 1797-1808. https://doi.org/10.1016/S0008-8846(98)00165-3
  38. Yeh, I.C. (2006), "Analysis of strength of concrete using design of experiments and neural networks", J. Mater. Civil Eng., 18(4), 597-604. https://doi.org/10.1061/(ASCE)0899-1561.
  39. Yeh, I.C. and Lien, L.C. (2009), "Knowledge discovery of concrete material using genetic operation trees", Exp. Syst. Appl., 36(3), 5807-5812. https://doi.org/10.1016/j.eswa.2008.07.004.
  40. Zhu, L., Zhao, C. and Dai, J. (2021), "Prediction of compressive strength of recycled aggregate concrete based on gray correlation analysis", Constr. Build. Mater., 273, 121750. https://doi.org/10.1016/j.conbuildmat.2020.121750.